LeonLIU

icon indicating an email [email protected]

icon company City University of Hong Kong icon location Hong Kong icon location Research Student on Computer Vision and Deep Learning

Results 4 comments of LeonLIU

Share trained model

still missing.

How can i combine video and audio

+1

Do you have any plan to update reference-only in this repo?

waiting for this

Only output [1, 2] tokens for 'lmms-lab/LLaVA-NeXT-Video-7B-DPO' video demo inference

The command: `bash scripts/video/demo/video_demo.sh lmms-lab/LLaVA-NeXT-Video-7B-DPO vicuna_v1 32 2 True xxx.mp4` By the way, I found using pool_stride=4 can solve this, because the input token length with stride=2 is 4673 which...